Adding Evaluation Results

README.md

@@ -8,9 +8,112 @@ tags:
 - unsloth
 - mistral
 - trl
-base_model: alnrg2arg/blockchainlabs_7B_merged_test2_4
 datasets:
 - Open-Orca/SlimOrca
+base_model: alnrg2arg/blockchainlabs_7B_merged_test2_4
+model-index:
+- name: test3_sft_16bit
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 73.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_16bit
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 88.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_16bit
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_16bit
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 69.77
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_16bit
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 84.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_16bit
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 70.43
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_16bit
+      name: Open LLM Leaderboard
 ---
 
 # Uploaded  model
@@ -105,4 +208,17 @@ Benchmark scores
 
 
 
-Average 75.94
+Average 75.94
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_alnrg2arg__test3_sft_16bit)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.28|
+|AI2 Reasoning Challenge (25-Shot)|73.55|
+|HellaSwag (10-Shot)              |88.87|
+|MMLU (5-Shot)                    |64.63|
+|TruthfulQA (0-shot)              |69.77|
+|Winogrande (5-shot)              |84.45|
+|GSM8k (5-shot)                   |70.43|
+